{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WJDHXIHU46I5MWDBT2B3AZXDP7","short_pith_number":"pith:WJDHXIHU","schema_version":"1.0","canonical_sha256":"b2467ba0f4e791d658619e83b066e37fe3387cd88d4a58d773a1857d3ce0dfca","source":{"kind":"arxiv","id":"2303.09797","version":2},"attestation_state":"computed","paper":{"title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Wu, Hongwei Xu, Jelo Wang, Jia Jia, Junliang Xing, Xiangyuan Wang","submitted_at":"2023-03-17T06:43:08Z","abstract_excerpt":"Audio-Driven Face Animation is an eagerly anticipated technique for applications such as VR/AR, games, and movie making. With the rapid development of 3D engines, there is an increasing demand for driving 3D faces with audio. However, currently available 3D face animation datasets are either scale-limited or quality-unsatisfied, which hampers further developments of audio-driven 3D face animation. To address this challenge, we propose MMFace4D, a large-scale multi-modal 4D (3D sequence) face dataset consisting of 431 identities, 35,904 sequences, and 3.9 million frames. MMFace4D exhibits two c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.09797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T06:43:08Z","cross_cats_sorted":[],"title_canon_sha256":"65e84eb6d22e7069d29a157447e84b5f8c67e763ff7255be433c7a13fd78945c","abstract_canon_sha256":"e2c3f13690e0aa5836ecfb1ea8ba3df4b783c072953d2395d967ea572ae6d20b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:24.809329Z","signature_b64":"jpgabg+jxI4vt+xq5r7uP5Kep3ihjUM1duv4sZyjRN7kK+x3ZoEunaaa77WHyySa3GmWlZx/dMmzM+DYiQQIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2467ba0f4e791d658619e83b066e37fe3387cd88d4a58d773a1857d3ce0dfca","last_reissued_at":"2026-07-05T07:23:24.808891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:24.808891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Wu, Hongwei Xu, Jelo Wang, Jia Jia, Junliang Xing, Xiangyuan Wang","submitted_at":"2023-03-17T06:43:08Z","abstract_excerpt":"Audio-Driven Face Animation is an eagerly anticipated technique for applications such as VR/AR, games, and movie making. With the rapid development of 3D engines, there is an increasing demand for driving 3D faces with audio. However, currently available 3D face animation datasets are either scale-limited or quality-unsatisfied, which hampers further developments of audio-driven 3D face animation. To address this challenge, we propose MMFace4D, a large-scale multi-modal 4D (3D sequence) face dataset consisting of 431 identities, 35,904 sequences, and 3.9 million frames. MMFace4D exhibits two c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09797","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.09797/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.09797","created_at":"2026-07-05T07:23:24.808948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09797v2","created_at":"2026-07-05T07:23:24.808948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09797","created_at":"2026-07-05T07:23:24.808948+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJDHXIHU46I5","created_at":"2026-07-05T07:23:24.808948+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJDHXIHU46I5MWDB","created_at":"2026-07-05T07:23:24.808948+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJDHXIHU","created_at":"2026-07-05T07:23:24.808948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12438","citing_title":"Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7","json":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7.json","graph_json":"https://pith.science/api/pith-number/WJDHXIHU46I5MWDBT2B3AZXDP7/graph.json","events_json":"https://pith.science/api/pith-number/WJDHXIHU46I5MWDBT2B3AZXDP7/events.json","paper":"https://pith.science/paper/WJDHXIHU"},"agent_actions":{"view_html":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7","download_json":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7.json","view_paper":"https://pith.science/paper/WJDHXIHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09797&json=true","fetch_graph":"https://pith.science/api/pith-number/WJDHXIHU46I5MWDBT2B3AZXDP7/graph.json","fetch_events":"https://pith.science/api/pith-number/WJDHXIHU46I5MWDBT2B3AZXDP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7/action/storage_attestation","attest_author":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7/action/author_attestation","sign_citation":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7/action/citation_signature","submit_replication":"https://pith.science/pith/WJDHXIHU46I5MWDBT2B3AZXDP7/action/replication_record"}},"created_at":"2026-07-05T07:23:24.808948+00:00","updated_at":"2026-07-05T07:23:24.808948+00:00"}